Provides persistent memory storage for Windsurf (by Codeium), allowing the AI coding assistant to retain project context, decisions, and task state across sessions.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@memory-mcp-lite remind me of the caching decision we made last week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A small, opinionated memory server for AI coding assistants (Windsurf, Cursor, Claude Desktop — anything that speaks MCP).
It runs locally, stores durable knowledge on your disk, and tries very hard to stay out of your agent's way until you actually need it.
Most AI clients already have some form of short-term memory. They remember the current conversation, maybe a few rules you've set, and that's about it. What they don't give you is a place to park things that should outlive the session — the architectural decision you made last week, the one weird build command for this repo, the gotcha that bit you three times in a row.
memory-mcp-lite is that place. It stores:
technical decisions and the reasoning behind them,
project architecture and conventions,
commands, env notes, links, and gotchas,
task state so you can resume work later,
rolled-up summaries at the global / project / task level.
It deliberately does not store raw chat transcripts, replace your client's built-in rules, run embeddings or vector search, or need a server or cloud connection.
Related MCP server: Mind Keg MCP
Memory lives in a tree:
global
└── project
├── [project_summary]
└── task
├── [task_summary]
└── atomic // decision | fact | gotcha | command | link | conventionOn top of the tree you can draw optional graph-lite edges between any two nodes — related_to, depends_on, affects, caused_by, supersedes, references. Handy when one decision obsoletes another, or a gotcha only matters in the context of a specific command.
The retrieval side is built to be cheap. The server's instructions push agents through three stages, from least to most expensive:
Stage 1 — summaries get_global_summary / get_project_summary / get_task_summary
│
▼ (only if summaries aren't enough)
Stage 2 — FTS5 light search search_memory_light → compact candidates
│
▼ (only for the 1–3 most relevant hits)
Stage 3 — full detail get_memory_detailIn practice this means your agent asks for a summary first, and only pays for the big payload when it has a specific reason to. If you skip this policy, you just end up dumping a bunch of stringly-typed JSON into context for no reason.
TypeScript, Node ≥ 20
Drizzle ORM over libSQL (@libsql/client)
SQLite FTS5 for lexical search
A closure table for efficient subtree traversal
The MCP TypeScript SDK (@modelcontextprotocol/sdk)
You can point it at a local file, a remote libSQL instance, or a Turso database — they all work the same.
The fast path is to let your MCP client fetch the package via npx.
Windsurf — ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"memory-mcp-lite": {
"command": "npx",
"args": ["memory-mcp-lite"]
}
}
}Claude Desktop — ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"memory-mcp-lite": {
"command": "npx",
"args": ["memory-mcp-lite"]
}
}
}Same pattern for any other MCP-compatible client; only the config file path changes.
npm install
npm run build # outputs dist/index.js; the schema is created on first runThen point your client at the compiled bundle:
{
"mcpServers": {
"memory-mcp-lite": {
"command": "node",
"args": ["/absolute/path/to/memory-mcp-lite/dist/index.js"]
}
}
}If you want to iterate on the code without a build step, tsx works:
{
"mcpServers": {
"memory-mcp-lite": {
"command": "npx",
"args": ["tsx", "/absolute/path/to/memory-mcp-lite/apps/server/src/index.ts"]
}
}
}By default: ~/.memory-mcp/memory.db. Override it with any of:
Env var | Purpose |
| Full path or |
| Directory; the file is still |
| Accepted for backwards compatibility. |
| Bearer token for remote libSQL / Turso. |
So running against Turso is just:
MEMORY_DB_PATH="libsql://your-db.turso.io" \
MEMORY_DB_AUTH_TOKEN="eyJhbGci..." \
npm run devNine tools, all returning both a human-readable JSON block and a structuredContent object for programmatic clients. The server also ships a strict description and annotations payload for each tool so agents can pick the right one without guessing.
Tool | Reach for it when… |
| recurring preferences, cross-project conventions |
| architecture, key decisions, long-term project context |
| resuming a specific piece of work |
| summaries aren't enough; you want compact candidates |
| you've picked a candidate and need the full body |
| an architecture choice, trade-off, or rejected path |
| a command, env note, gotcha, link, or convention |
| after an arch change or new convention worth recording |
| after progress, blockers, or a plan change |
The retrieval discipline the server asks agents to follow:
summaries first,
light search only if summaries aren't enough,
full detail for at most 1–3 hits,
never dump every memory just because you can.
Projects are looked up in this priority order:
Normalised git remote URL — the most stable; survives directory moves and clones.
Git root path — used when there's no remote.
Normalised workspace path — the fallback.
This means the same project keeps the same memory even if different clients hand you slightly different paths, and moving a repo doesn't orphan everything you've stored.
npm run typecheck # TypeScript
npm run lint # oxlint
npm run test # vitest
npm run build # esbuild bundle to dist/
npm run dev # tsx watch
npm run db:studio # Drizzle Studio for poking at the DB
npm run db:generate # generate migration SQL when the schema changesThe schema is defined in apps/server/src/db/schema.ts and re-asserted on every startup by ensureSchema() (see apps/server/src/db/migrate.ts). That function is also where the FTS5 virtual table and its triggers get created — Drizzle doesn't manage virtual tables, so we do it ourselves with plain SQL. It's idempotent, so there's nothing to run manually.
Optional semantic fallback (local embeddings, feature-flagged).
Node archival / cleanup for long-lived projects.
Shared-team memory, once there's a good story for auth.
Return the user's cross-project global memory summary (coding style, recurring preferences, stable workflow conventions). USE WHEN: the request depends on durable user-level preferences that apply across projects. DO NOT USE WHEN: the question is project-specific, purely syntactic, or self-contained. RETURNS: { found, summary? } where summary has { id, title, summary, updated_at }.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| found | Yes | |
| summary | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds value by detailing the output structure ('{ found, summary? }' with fields) and clarifying the durable user-level nature of the preferences, but does not contradict annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: two sentences for purpose, two for usage, one for returns. Front-loaded with the core action, no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and an output schema described in the text (structure of return object), the description is fully sufficient. Annotations cover safety and idempotency.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. The description adds no parameter info beyond the schema, which is appropriate per the baseline of 4 for zero-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns a 'cross-project global memory summary' and lists its contents ('coding style, recurring preferences, stable workflow conventions'). It is distinct from siblings like 'get_project_summary' and 'get_task_summary' by specifying the global scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit 'USE WHEN' and 'DO NOT USE WHEN' rules provide clear context for when to invoke this tool, including exclusions for project-specific, syntactic, or self-contained questions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Load the full body of a specific memory by id. USE WHEN: a search_memory_light candidate looks relevant and you need its full content / metadata. DO NOT USE WHEN: you have not identified a specific memory id, or you are tempted to call this many times in a row. LIMIT: call at most 3 times per user turn. RETURNS: { found, memory? } where memory has { id, title, summary, content, memory_type, level, importance, source, metadata, created_at, updated_at }.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Memory node id as returned by search_memory_light (e.g. 'mem_<hex>') |
| Name | Required | Description |
|---|---|---|
| found | Yes | |
| memory | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive traits. The description adds behavioral context: the return structure ({ found, memory? } with full detail) and the call limit. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four concise sentences: purpose, USE WHEN, DO NOT USE WHEN, LIMIT, RETURNS. Front-loaded with purpose, every sentence adds value, no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Fully covers purpose, usage, behavior, parameter, and return value. With rich annotations and output schema, the description fills all remaining gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds context: the id comes from search_memory_light and gives an example format 'mem_<hex>'. This goes beyond the schema's minimal 'Memory node id' description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Load the full body of a specific memory by id.' It uses a specific verb ('Load') and resource ('memory detail'), and distinguishes from siblings like search_memory_light (candidates) and summary tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'USE WHEN: a search_memory_light candidate looks relevant...' and 'DO NOT USE WHEN: you have not identified a specific memory id...' plus a limit of 3 calls per turn. This provides clear when/when-not guidance with alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the concise summary for the current project (architecture, key decisions, conventions). USE WHEN: the request depends on project-level context — architecture, conventions, long-term decisions, or project overview. DO NOT USE WHEN: the request is about the current task's state, global preferences, or is self-contained. CALL ORDER: prefer this before search_memory_light. Pass workspace_path OR git_root OR remote_url OR project_id so the server can identify the project. RETURNS: { project_id, found, summary? } where summary has { id, title, summary, updated_at }.
| Name | Required | Description | Default |
|---|---|---|---|
| git_root | No | Absolute path to the git repository root | |
| project_id | No | Explicit project id (skip auto-resolution when known) | |
| remote_url | No | Git remote URL, e.g. https://github.com/org/repo | |
| workspace_path | No | Absolute path to the workspace root, e.g. /Users/me/code/app |
| Name | Required | Description |
|---|---|---|
| found | Yes | |
| summary | Yes | |
| project_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint. Description adds context about project identification method (one of four parameters) and return structure, including that summary contains id, title, summary, updated_at. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is well-structured with clear sections (USE WHEN, DO NOT USE WHEN, CALL ORDER, RETURNS). Every sentence adds value, no redundancy. Front-loaded with core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given rich annotations (readOnlyHint, idempotentHint) and presence of output schema, the description covers all essential aspects: purpose, usage conditions, parameter guidance, and return structure. No obvious gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds crucial information: parameter selection logic (can pass workspace_path OR git_root OR remote_url OR project_id) and explains when to use project_id (explicit vs auto-resolution). This goes beyond the schema's individual parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description uses specific verb 'Return' and resource 'project summary', listing content (architecture, key decisions, conventions). It distinguishes from siblings like get_task_summary and get_global_summary by specifying project-level context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly includes 'USE WHEN' and 'DO NOT USE WHEN' sections with concrete conditions. Provides 'CALL ORDER' recommending preference over search_memory_light, giving clear guidance for agent decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the current task summary (what was done, blockers, next steps). USE WHEN: the user asks to continue, resume, or recall recent work on a task. DO NOT USE WHEN: there is no prior task state referenced, or the request is about global / project-level context. RETURNS: { project_id, found, summary? } where summary has { id, title, summary, updated_at }.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | No | Optional task node id to scope the summary to | |
| git_root | No | Absolute path to the git repository root | |
| project_id | No | Explicit project id | |
| remote_url | No | Git remote URL for the project | |
| workspace_path | No | Absolute path to the workspace root |
| Name | Required | Description |
|---|---|---|
| found | Yes | |
| summary | Yes | |
| project_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description's safety profile is clear. The description adds value by specifying the return structure and summarizing what the summary contains, which goes beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Every sentence is purposeful and the description uses clear headers (USE WHEN, DO NOT USE WHEN, RETURNS) for easy parsing. It is concise with zero redundant phrases.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema and complete parameter schema, the description adequately covers the tool's purpose and usage. It lacks only minor details on parameter interactions, but these are not essential given schema coverage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with all five parameters described. The description does not add further parameter semantics beyond what the schema already provides, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns the current task summary including what was done, blockers, and next steps. It explicitly distinguishes from sibling tools that handle global or project-level contexts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides specific WHEN to use (user asks to continue, resume, or recall recent work) and explicit DO NOT USE conditions (no prior task state or global/project context). This is exemplary guidance for an AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Persist a durable technical decision (architecture choice, trade-off, accepted pattern, rejected alternative). USE WHEN: the user confirms a decision that should outlive the current session. DO NOT USE WHEN: the info is a transient fact/command (use remember_fact) or raw chat log. IMPORTANCE: defaults to 0.8 — override only if the user signals otherwise. RETURNS: { project_id, memory_id }.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Short, specific title for the decision (max 200 chars) | |
| source | No | Optional source pointer (file path, PR url, doc link) | |
| content | No | Optional extended rationale, trade-offs, and rejected alternatives | |
| summary | Yes | One-paragraph summary: what was decided and the primary reason (max 500 chars) | |
| git_root | No | Absolute path to the git repository root | |
| importance | No | 0.0-1.0, defaults to 0.8 for decisions | |
| project_id | No | Explicit project id | |
| remote_url | No | Git remote URL | |
| workspace_path | No | Absolute path to the workspace root |
| Name | Required | Description |
|---|---|---|
| memory_id | Yes | |
| project_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are minimal (all false), so the description carries the burden. It discloses that the tool persists data durably, returns { project_id, memory_id }, and specifies a default importance. It does not explicitly state whether it creates new records or updates existing ones, but the context suggests creation. This is sufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: a single purpose sentence, followed by usage conditions, a default value note, and return format. Every sentence earns its place without redundancy. It is well front-loaded with the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 9 parameters, 2 required, and a known output shape, the description covers the essential usage, distinguishes from the main sibling, and notes defaults. It could mention that the tool creates a new memory entry (implied but not explicit) and hint at how the output IDs are used. However, it is largely complete for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all parameters are already documented in the schema. The description adds only minimal value by reiterating the default importance and emphasizing that the user must confirm a decision. No additional semantic meaning beyond schema is provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool persists durable technical decisions, listing examples (architecture choice, trade-off, etc.) and explicitly distinguishes it from the sibling tool remember_fact. The verb 'Persist' and resource 'technical decision' are specific and actionable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit 'USE WHEN' and 'DO NOT USE WHEN' conditions, naming the alternative tool remember_fact. While it doesn't cover all siblings, it effectively prevents the most common misuse. Slightly more comprehensive inclusion of other siblings would improve it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Persist a concise atomic memory: fact, command, gotcha, link, or convention. USE WHEN: the user gives concrete reusable info (a command, env detail, integration note, rule). DO NOT USE WHEN: the info is a major decision (use remember_decision) or a summary (use upsert_*_summary). FACT TYPES: fact | command | gotcha | link | convention | decision (prefer remember_decision for 'decision'). RETURNS: { project_id, memory_id }.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Short title for the fact (max 200 chars) | |
| source | No | Optional source pointer (file path, PR url, doc link) | |
| content | No | Optional extended detail or example usage | |
| summary | Yes | Concise fact body (max 500 chars) | |
| git_root | No | Absolute path to the git repository root | |
| fact_type | No | Atomic memory type: fact | command | gotcha | link | convention | decision. Prefer remember_decision for 'decision'. | fact |
| importance | No | 0.0-1.0, defaults to the type-specific default in MemoryPolicy | |
| project_id | No | Explicit project id | |
| remote_url | No | Git remote URL | |
| workspace_path | No | Absolute path to the workspace root |
| Name | Required | Description |
|---|---|---|
| memory_id | Yes | |
| project_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false, destructiveHint=false. The description adds that it returns {project_id, memory_id} and provides fact type guidance. No contradictions, but could mention idempotency (idempotentHint=false).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Every sentence adds value: purpose, usage, types, return. Front-loaded, no fluff, well-structured with section headings.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 10 parameters, 100% schema coverage, and output schema, the description covers purpose, usage, and return. Minor gap: no mention of overwrite or duplicate behavior, but annotations and schema handle most.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline 3. Description adds context for fact_type enum and its preferred usage, improving parameter understanding beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'persist' and resource 'atomic memory', and distinguishes from sibling tools like remember_decision and upsert summaries by specifying concrete, reusable info types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit USE WHEN and DO NOT USE WHEN sections provide clear context and name alternatives (remember_decision for decisions, upsert summaries for summaries).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Lexical FTS5 search across atomic memories. Returns compact candidate records only — not full content. USE WHEN: the summary tools above do not provide enough context AND the request includes a concrete search phrase (command name, symbol, past event). DO NOT USE WHEN: summaries already answer the question, the query is empty/too vague, or you only need the global/project/task summary. CALL ORDER: always call summary tools first. Then follow up this tool's top 1-3 results with get_memory_detail — never dump all candidates. RETURNS: { count, results: [{ id, title, summary, memory_type, level, importance, updated_at }] }.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max candidate results, 1-20. Defaults to 10. | |
| query | Yes | Free-text search query — a keyword, command, or phrase | |
| scope | No | Search scope: 'project' (scoped to resolved project) or 'global' (all projects). | project |
| git_root | No | Absolute path to the git repository root | |
| project_id | No | Explicit project id | |
| remote_url | No | Git remote URL | |
| workspace_path | No | Absolute path to the workspace root |
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds that it returns compact candidates (not full content) and describes the return shape. Provides search type (FTS5) and call-order context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise, well-structured with labeled sections. Every sentence is informative; no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given output schema (in description), good annotations, and full schema coverage, the description fully informs the agent about behavior, usage, and results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline 3 is appropriate. The description does not add extra meaning beyond schema descriptions, but does not need to.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it's a lexical FTS5 search across atomic memories and that it returns compact candidate records, not full content. Distinct from siblings like get_memory_detail.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit WHEN, DO NOT USE, and CALL ORDER sections. Specifies when to use (summaries insufficient + concrete search phrase) and when not, and prescribes calling summary tools first then get_memory_detail for top results.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Idempotently create or replace the structured project summary node. USE WHEN: architecture, conventions, or key decisions changed enough that a fresh summary is worth storing. DO NOT USE WHEN: the change is a single fact / decision (use remember_fact or remember_decision). RETURNS: { project_id, summary_id }.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Project summary title, e.g. 'MyApp Project Overview' | |
| summary | Yes | Structured project summary: stack, key decisions, conventions, architecture (max 2000 chars) | |
| git_root | No | Absolute path to the git repository root | |
| project_id | No | Explicit project id | |
| remote_url | No | Git remote URL | |
| display_name | No | Human-readable project name (displayed to users) | |
| workspace_path | No | Absolute path to the workspace root |
| Name | Required | Description |
|---|---|---|
| project_id | Yes | |
| summary_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond annotations: it explicitly states idempotency ('Idempotently'), the create-or-replace nature, and the return value shape ({ project_id, summary_id }). No contradiction with annotations (idempotentHint=true, destructiveHint=false).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: three sentences covering purpose, usage conditions, and return value. Every sentence is necessary and front-loaded with the most critical information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the 7 parameters, annotations, and output schema (mentioned), the description covers usage guidelines and return value. However, it does not explain how the parameters (e.g., project_id vs git_root) interact to identify the project, which is a minor gap for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with per-parameter descriptions in the schema. The tool description does not add extra meaning beyond the schema; it only mentions the return value. Baseline score of 3 is appropriate as the schema already carries the semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Idempotently create or replace the structured project summary node', specifying the verb (create/replace) and resource (project summary). It distinguishes from sibling tools like remember_fact and remember_decision by indicating granularity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit 'USE WHEN' and 'DO NOT USE WHEN' conditions, stating that it is for major changes (architecture, conventions) and not for single facts/decisions, with direct references to alternative tools (remember_fact, remember_decision).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Idempotently create or replace the current task summary (progress, blockers, next steps). USE WHEN: meaningful progress was made, a blocker appeared, or the plan changed and the next session must resume. DO NOT USE WHEN: the update fits better as a single fact or decision. RETURNS: { project_id, summary_id }.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Short task title, e.g. 'Implement auth middleware' | |
| summary | Yes | Current task state: what was done, blockers, next steps (max 2000 chars) | |
| git_root | No | Absolute path to the git repository root | |
| project_id | No | Explicit project id | |
| remote_url | No | Git remote URL | |
| parent_task_id | No | Optional parent task node id for nesting | |
| workspace_path | No | Absolute path to the workspace root |
| Name | Required | Description |
|---|---|---|
| project_id | Yes | |
| summary_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare idempotentHint: true, readOnlyHint: false, destructiveHint: false. The description adds 'idempotently create or replace,' aligns with idempotence, and discloses return format ({ project_id, summary_id }). It explains the summary structure (progress, blockers, next steps), adding behavioral context beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise: two lines for main description, then USE WHEN, DO NOT USE WHEN, and RETURNS. No unnecessary words; each sentence adds value. Front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers what, when, and what-not well. Output schema is described via return format. Sibling context is clear. Minor gap: no explanation of which parameter uniquely identifies the summary for update, but overall it's quite complete for an upsert tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter described. The description does not add extra semantics beyond the schema; however, it does not clarify how the tool identifies the task to update (e.g., whether title or project_id serves as key). Baseline 3 is appropriate given thorough schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Idempotently create or replace the current task summary (progress, blockers, next steps).' This specifies the operation (upsert), the resource (task summary), and its content. It distinguishes from siblings like get_task_summary (read) and upsert_project_summary (project-level).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit 'USE WHEN' and 'DO NOT USE WHEN' conditions are provided: 'meaningful progress was made, a blocker appeared, or the plan changed' and 'the update fits better as a single fact or decision.' This directly guides the agent on appropriate contexts and alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v2.0.0get_global_summaryget_memory_detailget_project_summaryget_task_summaryremember_decisionremember_factsearch_memory_lightupsert_project_summaryupsert_task_summaryEach tool targets a distinct scope or action: summaries by level (global/project/task), retrieval (search vs detail), and persistence (fact vs decision vs summary upsert). No two tools have ambiguous boundaries.
All tool names follow a consistent verb_noun pattern in snake_case (get_*, search_*, remember_*, upsert_*). The naming is predictable and clearly conveys each tool's purpose.
With 9 tools, the server covers reading (3), searching (1), retrieving (1), remembering (2), and updating (2) summaries. This is well-scoped for a lightweight memory system.
The tool set covers the core memory operations: read summaries at three levels, search, detail retrieval, and persist facts/decisions/summaries. Minor omission: no upsert_global_summary, but the domain is 'lite' and the gap is acceptable.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.
Persistent memory for AI agents. Search and store durable facts, preferences and decisions.
Long-term memory for AI assistants. Hybrid retrieval, query expansion, auto-topics.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/thuupx/memory-mcp-lite'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
